ppo-Huggy / run_logs /timers.json
zwse's picture
Huggy
653124a verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.436220407485962,
"min": 1.4190754890441895,
"max": 1.436224341392517,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71266.6953125,
"min": 69288.4296875,
"max": 78276.203125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 143.16521739130434,
"min": 119.72222222222223,
"max": 409.7295081967213,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49392.0,
"min": 49156.0,
"max": 50239.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999677.0,
"min": 49895.0,
"max": 1999677.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999677.0,
"min": 49895.0,
"max": 1999677.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.2492895126342773,
"min": 0.05811086669564247,
"max": 2.425077199935913,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 776.0048828125,
"min": 7.612523555755615,
"max": 1003.98193359375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.0773618299028147,
"min": 1.6728857881922758,
"max": 3.777564290194105,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1061.689831316471,
"min": 207.12518337368965,
"max": 1433.284005701542,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.0773618299028147,
"min": 1.6728857881922758,
"max": 3.777564290194105,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1061.689831316471,
"min": 207.12518337368965,
"max": 1433.284005701542,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.00024375196274680394,
"min": 0.00010272374013058854,
"max": 0.0007604692970441344,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0004875039254936079,
"min": 0.0002660609871630489,
"max": 0.0019223984151418942,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.09927515188852945,
"min": 0.022033580475383337,
"max": 0.12254652505119643,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1985503037770589,
"min": 0.04617932252585888,
"max": 0.3573314920067787,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.198073600675003e-06,
"min": 4.198073600675003e-06,
"max": 0.00029534805155065,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.396147201350005e-06,
"min": 8.396147201350005e-06,
"max": 0.0008440171686609499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.09888054,
"min": 0.02124052,
"max": 0.09888054,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.19776108,
"min": 0.04248104,
"max": 0.29048456,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.982631750000006e-05,
"min": 7.982631750000006e-05,
"max": 0.0049226225650000005,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00015965263500000013,
"min": 0.00015965263500000013,
"max": 0.014068818595000001,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1732166901",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1732168827"
},
"total": 1926.153210077,
"count": 1,
"self": 0.3210813010000493,
"children": {
"run_training.setup": {
"total": 0.0570032389998687,
"count": 1,
"self": 0.0570032389998687
},
"TrainerController.start_learning": {
"total": 1925.7751255370001,
"count": 1,
"self": 3.719006722981476,
"children": {
"TrainerController._reset_env": {
"total": 5.024319289999994,
"count": 1,
"self": 5.024319289999994
},
"TrainerController.advance": {
"total": 1916.9174162320185,
"count": 228446,
"self": 3.83075091198225,
"children": {
"env_step": {
"total": 1518.4712624130098,
"count": 228446,
"self": 1156.9467819211056,
"children": {
"SubprocessEnvManager._take_step": {
"total": 359.0527353519176,
"count": 228446,
"self": 13.832543645992473,
"children": {
"TorchPolicy.evaluate": {
"total": 345.2201917059251,
"count": 222860,
"self": 345.2201917059251
}
}
},
"workers": {
"total": 2.471745139986524,
"count": 228446,
"self": 0.0,
"children": {
"worker_root": {
"total": 1918.8057364309204,
"count": 228446,
"is_parallel": true,
"self": 988.6164229549656,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008702659999926254,
"count": 1,
"is_parallel": true,
"self": 0.0002618539999730274,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000608412000019598,
"count": 2,
"is_parallel": true,
"self": 0.000608412000019598
}
}
},
"UnityEnvironment.step": {
"total": 0.02192506999995203,
"count": 1,
"is_parallel": true,
"self": 0.00026933600020129234,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00015919199995551025,
"count": 1,
"is_parallel": true,
"self": 0.00015919199995551025
},
"communicator.exchange": {
"total": 0.0209825079998609,
"count": 1,
"is_parallel": true,
"self": 0.0209825079998609
},
"steps_from_proto": {
"total": 0.0005140339999343269,
"count": 1,
"is_parallel": true,
"self": 0.00017264799998883973,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00034138599994548713,
"count": 2,
"is_parallel": true,
"self": 0.00034138599994548713
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 930.1893134759548,
"count": 228445,
"is_parallel": true,
"self": 25.312844381856394,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 48.355140373060294,
"count": 228445,
"is_parallel": true,
"self": 48.355140373060294
},
"communicator.exchange": {
"total": 798.5238192920501,
"count": 228445,
"is_parallel": true,
"self": 798.5238192920501
},
"steps_from_proto": {
"total": 57.997509428987996,
"count": 228445,
"is_parallel": true,
"self": 22.471771338065764,
"children": {
"_process_rank_one_or_two_observation": {
"total": 35.52573809092223,
"count": 456890,
"is_parallel": true,
"self": 35.52573809092223
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 394.61540290702646,
"count": 228446,
"self": 5.8750789810210335,
"children": {
"process_trajectory": {
"total": 122.93725359500286,
"count": 228446,
"self": 122.71696917700274,
"children": {
"RLTrainer._checkpoint": {
"total": 0.22028441800011933,
"count": 1,
"self": 0.22028441800011933
}
}
},
"_update_policy": {
"total": 265.8030703310026,
"count": 96,
"self": 232.34498343499672,
"children": {
"TorchPPOOptimizer.update": {
"total": 33.45808689600585,
"count": 288,
"self": 33.45808689600585
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0759999895526562e-06,
"count": 1,
"self": 1.0759999895526562e-06
},
"TrainerController._save_models": {
"total": 0.1143822160001946,
"count": 1,
"self": 0.002138377000392211,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11224383899980239,
"count": 1,
"self": 0.11224383899980239
}
}
}
}
}
}
}